woodpecker-mcp

woodpecker_secrets

Destructive

Manage Woodpecker CI repository, organization, and global secrets: list, get metadata, create, update, or delete entries; write actions run only with explicit confirmation.

Instructions

Repository, organization, and global secret list, get, create, update, and delete. Secret values are write-only and redacted. Writes run only when confirm is true and WOODPECKER_ALLOW_WRITES=true. Actions: list, get, create, update, delete, org_list, org_get, org_create, org_update, org_delete, global_list, global_get, global_create, global_update, global_delete.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "action": "<action>"
    },
    "name": "woodpecker_secrets"
  }
}

Input Schema

Name	Required	Description
`name`	No
`note`	No
`page`	No
`value`	No
`action`	Yes	Woodpecker operation to call.
`events`	No
`images`	No
`org_id`	No
`secret`	No
`confirm`	No	Boolean true runs the write when WOODPECKER_ALLOW_WRITES is true. Omit it or pass false for a dry-run preview that sends nothing. The string true is rejected.
`perPage`	No
`repo_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 11, 2026

TDQS

B3.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations, it discloses two non-obvious behaviors: secret values are write-only and redacted on read, and writes require both confirm=true and the WOODPECKER_ALLOW_WRITES environment flag, with omission producing a dry run. That materially changes agent behavior and is not inferable from the destructiveHint/readOnlyHint flags alone. It stops short of noting permission scopes or per-action rate/error behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence and the write-gating sentence are front-loaded and earn their place, but the trailing 'Actions: list, get, create, ...' list restates the action enum verbatim from the schema, adding length without adding meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a high-complexity tool: 12 parameters, 15 actions, no output schema, and thin schema descriptions. The definition covers the write-safety contract but leaves critical gaps — which parameters are required per action, what get/list return (redacted values, pagination via page/perPage) — so an agent cannot reliably construct most calls from this text alone.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 17% across 12 parameters, and the description explains only 'confirm' and the write-only nature of 'value'. It gives no mapping for repo_id, org_id, secret, name, note, events, images, page, or perPage to specific actions, leaving the agent to guess which fields each action consumes.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource precisely (repository, organization, and global secrets) and enumerates the verbs (list/get/create/update/delete), so the agent knows exactly what domain and operations this tool covers. Sibling tools (cron, logs, pipelines, repos, system) are different domains, so no explicit differentiation is needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied through the scope prefixes (org_*, global_*) and the confirm gate, but there is no explicit statement of when to choose org_* versus global_* versus the bare repo actions, nor prerequisites such as which identifiers each action needs. The when-to-write rule is stated clearly; the when-to-use-which-action rule is not.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server